Model comparison
Gemini 3.7 Flash vs Llama 2-70B
Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 24.1 on the Noometry Index.
Last verified . 21 shared benchmarks.
Google
MetaSummary
- They share 21 benchmarks with published results for both. Gemini 3.7 Flash scores higher in 8 categories and Llama 2-70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.7 Flash leads 69.8 to 7.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 97.2% for Gemini 3.7 Flash and 0% for Llama 2-70B.
- Llama 2-70B has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.7 Flash | Llama 2-70B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 59.8 | 24.1 |
| Released | 2026-08-13 | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.75 | — |
| Output $ / M tokens | $3.75 | — |
| Results tracked | 44 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.7 Flash leads
Gemini 3.7 Flash: 55.7 (#19), Llama 2-70B: 30.8 (#281)
| Benchmark | Gemini 3.7 Flash | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1499 | 1079 |
| DeepSWE | 65.5% | — |
| FrontierCode | 43.6% | — |
| LMArena WebDev | 1593 | — |
| FrontierSWE | 20.3% | — |
| SciCode | 59.8% | — |
| ALE-Bench | 904.3 | — |
Agentic & Tool Use Not comparable
Gemini 3.7 Flash: 42.2 (#18), Llama 2-70B: —
| Benchmark | Gemini 3.7 Flash | Llama 2-70B |
|---|---|---|
| APEX-Agents | 67.8% | — |
| Remote Labor Index | 5% | — |
| GDP.pdf | 23.8% | — |
Reasoning Gemini 3.7 Flash leads
Gemini 3.7 Flash: 70.1 (#12), Llama 2-70B: 13.7 (#324)
| Benchmark | Gemini 3.7 Flash | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1497 | 1073 |
| DTBench | 96.8% | 41.6% |
| Epoch Capabilities Index | 157.72 | 113.59 |
| ARC-AGI-2 | 84.6% | — |
| NYT Connections (extended) | 94% | — |
| ARC-AGI-1 | 95.5% | — |
| CritPt | 14.3% | — |
| Chess Puzzles | 47% | — |
| Mystery Game Puzzles | 37% | — |
| LMCA | 50.4% | — |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |
Math Gemini 3.7 Flash leads
Gemini 3.7 Flash: 69.5 (#18), Llama 2-70B: 7.5 (#320)
| Benchmark | Gemini 3.7 Flash | Llama 2-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 97.2% | 0% |
| LMArena Math | 1511 | 1091 |
| FrontierMath (Tiers 1-3) | 71.6% | — |
| FrontierMath Tier 4 | 36.6% | — |
| ProofBench | 58% | — |
| MATH Level 5 | — | 3.3% |
| GSM8K | — | 69.6% |
Knowledge Gemini 3.7 Flash leads
Gemini 3.7 Flash: 69.8 (#4), Llama 2-70B: 7.4 (#305)
| Benchmark | Gemini 3.7 Flash | Llama 2-70B |
|---|---|---|
| GPQA Diamond | 94.8% | 26.3% |
| LMArena Expert | 1508 | 1039 |
| SimpleQA Verified | 69.2% | — |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multimodal Not comparable
Gemini 3.7 Flash: 36.9 (#69), Llama 2-70B: —
| Benchmark | Gemini 3.7 Flash | Llama 2-70B |
|---|---|---|
| LMArena Vision | 1314 | — |
| Furniture Assembly | 26.7% | — |
Multilingual Gemini 3.7 Flash leads
Gemini 3.7 Flash: 57.8 (#7), Llama 2-70B: 27.9 (#269)
| Benchmark | Gemini 3.7 Flash | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1485 | 1045 |
| LMArena Chinese | 1553 | 994 |
| LMArena French | 1512 | 1089 |
| LMArena German | 1485 | 1041 |
| LMArena Japanese | 1506 | 927 |
| LMArena Korean | 1486 | 964 |
| LMArena Russian | 1519 | 1083 |
| LMArena Spanish | 1507 | 1142 |
Instruction Following Gemini 3.7 Flash leads
Gemini 3.7 Flash: 78.0 (#12), Llama 2-70B: 55.1 (#273)
| Benchmark | Gemini 3.7 Flash | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1486 | 1071 |
Long Context Gemini 3.7 Flash leads
Gemini 3.7 Flash: 45.8 (#28), Llama 2-70B: 32.2 (#265)
| Benchmark | Gemini 3.7 Flash | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1493 | 1062 |
Writing & Preference Gemini 3.7 Flash leads
Gemini 3.7 Flash: 71.4 (#19), Llama 2-70B: 32.5 (#274)
| Benchmark | Gemini 3.7 Flash | Llama 2-70B |
|---|---|---|
| LMArena Text | 1487 | 1115 |
| LMArena Creative Writing | 1490 | 1075 |
| LMArena Multi-Turn | 1495 | 1088 |
| EQ-Bench Creative Writing | 1723 | — |
Frequently asked questions
Is Gemini 3.7 Flash better than Llama 2-70B?
Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 24.1 on the Noometry Index.
Is Gemini 3.7 Flash or Llama 2-70B better for coding?
Gemini 3.7 Flash scores higher on coding benchmarks: 55.7 versus 30.8 in the Noometry coding category.
How many benchmarks do Gemini 3.7 Flash and Llama 2-70B share?
21 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and Llama 2-70B has 35.